Skip to content

THGAgents: Traceable Biomedical Hypothesis Generation via Dynamic Causal Reasoning

· 0 citations · 41 references

TL;DR

THGAgents utilizes collaborative and dynamically updating agents to build a Traceable Causal Knowledge Graph, which serves as the foundation for the evidence-based knowledge structure and employs an LLM-driven heuristic search algorithm to traverse the complex network, balancing both novelty and rigor to deduce strict, evidence-based mechanistic causal chains.

View source

Similar papers

Book Open access Aug 2026

Knowledge Graph-Enhanced Long-CoT for Complex Biomolecular Reasoning

Results validate that KG-guided reasoning serves as a critical mechanism to compensate for parameter disparity, particularly in tasks requiring deep traversal of biological mechanisms.

Tianwen Lyu, Zhuang Xiang, Keyan Ding et al. · 0 citations
Open access Jul 2026

Agentic AI integrated with scientific knowledge: laboratory validation in systems biology.

Automation is transforming scientific discovery by enabling systematic exploration of complex hypotheses. Large language models (LLMs) perform well across diverse tasks and promise to accelerate research, but often struggle with logical structures. Here, we present a framework for biological discovery integrating LLM-based agents with laboratory automation, guided by logical scaffolds incorporating symbolic relational learning, structured vocabularies and experimental constraints. This integration improves coherence and reliability in automated workflows. We couple this AI-driven approach to automated cell-culture and metabolomics platforms, enabling integrated hypothesis validation and refinement, yielding a flexible discovery system. The system identified novel interactions in Saccharomyces cerevisiae, including glutamate-induced growth inhibition in spermine-treated cells and aminoadipate's partial rescue of formic-acid stress. All hypotheses, experiments and data are captured in a graph database employing controlled vocabularies. Existing ontologies are extended, and a novel representation of scientific hypotheses is presented using description logics. This work demonstrates the potential for a reliable machine-driven discovery process in systems biology.

Daniel Brunnsåker, Alexander H. Gower, Prajakta Naval et al. · 2 citations
Open access Aug 2026

EpiKG2DAG: a Framework for Automated DAG Construction from Biomedical Text

While Directed Acyclic Graphs (DAGs) are essential for causal inference, their construction often relies on expert heuristics, which bypasses systematic evidence synthesis and creates a critical "evidence retrieval gap" in causal modeling. This study introduces EpiKG2DAG, a framework that supports evidence-anchored candidate DAG generation by transforming unstructured biomedical abstracts into structured epidemiological associations. We utilized DeepSeek-V3 to extract exposure-outcome association triplets from 189,266 abstracts and employed SapBERT for semantic normalization against UMLS concepts. The resulting Epidemiological Knowledge Graph (EpiKG) enables the automated identification of candidate confounders, mediators, and colliders based on graph-theoretic motifs and literature-derived evidence. A case study on COVID-19 and AKI demonstrates that the framework uncovers non-obvious confounders, such as air pollution, while ensuring evidence traceability. This work contributes to the field by mitigating the knowledge-acquisition bottleneck and providing a transparent, reproducible foundation for evidence-based causal modeling.

J. Du, G. Deng · 0 citations

Optimizing large language model prompts for biomedical knowledge discovery

This work presents a scalable, reproducible framework for evaluating, optimizing, and interpreting LLMs for biomedical knowledge extraction, with a focus on gene–gene regulatory relation prediction, pathway component recognition, multimodal pathway figure understanding, and automated prompt optimization.

Muhammad Azam · 0 citations

Unveiling Biomedical Question Answering Pathways in Large Language Models: An Interpretability Study with Circuit Discovery

This study applies mechanistic interpretability techniques to uncover and analyze computational circuits within LLMs during biomedical question answering, and employs Automatic Circuit Discovery in combination with Edge Attribution Patching to enable scalable circuit extraction beyond toy settings.

Xilin Wang · 0 citations
Preprint Jul 2026

SciDataSailor: Deep Scientific Data Exploring

This work presents SciDataSailor, a framework for synthesizing tool-interactive trajectories by balancing broad exploration with targeted exploitation and presents SciDataSailor, a framework for synthesizing tool-interactive trajectories as Monte Carlo Tree Search (MCTS) with four task-specific mechanisms.

J. Rao, Yicheng Qiu, Chi Zhang et al. · 1 citation